hfslyc/AdvSemiSeg

Adversarial Learning for Semi-supervised Semantic Segmentation, BMVC 2018

42
/ 100
Emerging

This project helps researchers and developers in computer vision classify every pixel in an image into specific categories, even when only a small portion of their training data is meticulously labeled. It takes in images and their corresponding pixel-level labels (some fully labeled, some unlabeled) and outputs images with each pixel assigned to a semantic class. This tool is ideal for computer vision engineers and AI researchers working on image understanding tasks.

507 stars. No commits in the last 6 months.

Use this if you need to perform precise pixel-level classification (semantic segmentation) on images but have limited access to fully labeled datasets, allowing you to leverage vast amounts of unlabeled data.

Not ideal if you already have extensive, fully labeled datasets for your semantic segmentation task, as the benefits of semi-supervised learning might not outweigh the added complexity.

semantic-segmentation computer-vision image-analysis machine-learning-research data-efficient-learning
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 24 / 25

How are scores calculated?

Stars

507

Forks

124

Language

Python

License

Last pushed

Apr 21, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hfslyc/AdvSemiSeg"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.